Developing a real-time, robust, video tracker

K. Plakas, E. Trucco

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Tracking targets robustly in video sequences is a basic component for several image processing applications, including mosaicing, stabilization and shape/structure reconstruction from motion. We present recent developments of our work on a real-time video tracker, capable of tracking 30-50 feature points at 10-20 frames per second (depending on parameter settings) on a standard PC platform. Examples of tracking results with real mission sequences as well as laboratory tank data are shown. We also illustrate some applications where our real-time tracker has been successfully embedded in larger systems.

Original languageEnglish
Pages (from-to)1345-1352
Number of pages8
JournalOceans Conference Record
Volume2
Publication statusPublished - 2000
EventOceans 2000 - Providence, RI, USA
Duration: 11 Sep 200014 Sep 2000

Fingerprint Dive into the research topics of 'Developing a real-time, robust, video tracker'. Together they form a unique fingerprint.

Cite this